© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 15425
    Prev
    Next
    INDEX
    Explanations

    terms relating to conflict between opposing sides

    oai_token-act-pair · gemini-2.0-flash

    fighting against

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    numerusform
    -0.63
    ]^{-
    -0.54
    ◗
    -0.54
    eded
    -0.54
     @}
    -0.53
    substack
    -0.53
     retrouvé
    -0.53
     chi̍t
    -0.52
    quedo
    -0.52
    stdafx
    -0.52
    POSITIVE LOGITS
    AndEndTag
    0.81
     autorytatywna
    0.57
    ływ
    0.52
     mar
    0.51
    GOTREF
    0.49
    aryen
    0.48
     pymongo
    0.47
     ram
    0.46
    indakan
    0.46
    FailureListener
    0.46
    Activations Density 4.094%

    No Known Activations